Workshop registration closed! The facility to register for workshops has closed. If you have not registered for a workshop, workshop listings will be on the Message Board in the conference foyer of The Burlington Hotel for you to register for workshops that still have spaces available.

Introduction to meta-regression.

Julian Higgins and Judith Anzures.
MRC Biostatistics Unit, University of Cambridge, Cambridge, UK.

julian.higgins doesnotexist@cochrane.org mrc-bsu.cam.ac.uk


Objective: To train review authors and editors in some basic concepts of meta-regression.

Summary: Meta-regression is an extension to meta-analysis, and a generalization of subgroup analyses, that can be used to investigate heterogeneity of effects across studies. It examines the relationship between one or more study-level characteristics and the sizes of effect observed in the studies. Characteristics of studies might be, for example, aspects of the interventions, the settings or the designs (such as geographical location, dose of a drug, or length of treatment). The sizes of effects are the usual measures available for a meta-analysis, such as odds ratios or differences in means.

The workshop will provide an introduction to the method of meta-regression. We will consider when it might be useful for application in a Cochrane review, and will illustrate it using several examples. We will discuss in particular the limitations of meta-regression, including problems associated with looking at characteristics of participants, issues of power, the risk of false-positive results and availability of software. There will be ample opportunity to discuss the issues raised.


Level of knowledge required to attend: intermediate/advanced.